python>=3.8
torch>=1.13
torchaudio

pip3 install -U funasr

git clone https://github.com/alibaba/FunASR.git && cd FunASR
pip3 install -e ./

pip3 install -U modelscope huggingface huggingface_hub

funasr ++model=paraformer-zh ++vad_model="fsmn-vad" ++punc_model="ct-punc" ++input=asr_example_zh.wav

from funasr import AutoModel
from funasr.utils.postprocess_utils import rich_transcription_postprocess

model_dir = "iic/SenseVoiceSmall"

model = AutoModel(
    model=model_dir,
    vad_model="fsmn-vad",
    vad_kwargs={"max_single_segment_time": 30000},
    device="cuda:0",
)

# en
res = model.generate(
    input=f"{model.model_path}/example/en.mp3",
    cache={},
    language="auto",  # "zn", "en", "yue", "ja", "ko", "nospeech"
    use_itn=True,
    batch_size_s=60,
    merge_vad=True,  #
    merge_length_s=15,
)
text = rich_transcription_postprocess(res[0]["text"])
print(text)

from funasr import AutoModel
# paraformer-zh is a multi-functional asr model
# use vad, punc, spk or not as you need
model = AutoModel(model="paraformer-zh",  vad_model="fsmn-vad", punc_model="ct-punc", 
                  # spk_model="cam++"
                  )
res = model.generate(input=f"{model.model_path}/example/asr_example.wav", 
            batch_size_s=300, 
            hotword='魔搭')
print(res)

from funasr import AutoModel

chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention

model = AutoModel(model="paraformer-zh-streaming")

import soundfile
import os

wav_file = os.path.join(model.model_path, "example/asr_example.wav")
speech, sample_rate = soundfile.read(wav_file)
chunk_stride = chunk_size[1] * 960 # 600ms

cache = {}
total_chunk_num = int(len((speech)-1)/chunk_stride+1)
for i in range(total_chunk_num):
    speech_chunk = speech[i*chunk_stride:(i+1)*chunk_stride]
    is_final = i == total_chunk_num - 1
    res = model.generate(input=speech_chunk, cache=cache, is_final=is_final, chunk_size=chunk_size, encoder_chunk_look_back=encoder_chunk_look_back, decoder_chunk_look_back=decoder_chunk_look_back)
    print(res)

funasr-export ++model=paraformer ++quantize=false

from funasr import AutoModel

model = AutoModel(model="paraformer")

res = model.export(quantize=False)

# pip3 install -U funasr-onnx
from funasr_onnx import Paraformer
model_dir = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
model = Paraformer(model_dir, batch_size=1, quantize=True)

wav_path = ['~/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/example/asr_example.wav']

result = model(wav_path)
print(result)

@inproceedings{gao2023funasr,
  author={Zhifu Gao and Zerui Li and Jiaming Wang and Haoneng Luo and Xian Shi and Mengzhe Chen and Yabin Li and Lingyun Zuo and Zhihao Du and Zhangyu Xiao and Shiliang Zhang},
  title={FunASR: A Fundamental End-to-End Speech Recognition Toolkit},
  year={2023},
  booktitle={INTERSPEECH},
}
@inproceedings{An2023bat,
  author={Keyu An and Xian Shi and Shiliang Zhang},
  title={BAT: Boundary aware transducer for memory-efficient and low-latency ASR},
  year={2023},
  booktitle={INTERSPEECH},
}
@inproceedings{gao22b_interspeech,
  author={Zhifu Gao and ShiLiang Zhang and Ian McLoughlin and Zhijie Yan},
  title={{Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition}},
  year=2022,
  booktitle={Proc. Interspeech 2022},
  pages={2063--2067},
  doi={10.21437/Interspeech.2022-9996}
}
@article{shi2023seaco,
  author={Xian Shi and Yexin Yang and Zerui Li and Yanni Chen and Zhifu Gao and Shiliang Zhang},
  title={{SeACo-Paraformer: A Non-Autoregressive ASR System with Flexible and Effective Hotword Customization Ability}},
  year=2023,
  journal={arXiv preprint arXiv:2308.03266(accepted by ICASSP2024)},
}